Unseen Target Stance Detection with Adversarial Domain Generalization

TL;DR

This paper introduces an adversarial domain generalization method with attention-based encoding to improve stance detection on unseen targets, achieving state-of-the-art results on a benchmark dataset.

Contribution

It proposes a novel approach combining attention-based conditional encoding with adversarial training to address unseen target stance detection.

Findings

Achieves new state-of-the-art performance on SemEval-2016 dataset.

Highlights the importance of modeling domain differences between targets.

Demonstrates effectiveness of adversarial domain generalization in stance detection.

Abstract

Although stance detection has made great progress in the past few years, it is still facing the problem of unseen targets. In this study, we investigate the domain difference between targets and thus incorporate attention-based conditional encoding with adversarial domain generalization to perform unseen target stance detection. Experimental results show that our approach achieves new state-of-the-art performance on the SemEval-2016 dataset, demonstrating the importance of domain difference between targets in unseen target stance detection.